Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and Translate
Alignart: ترجمة الآلات العصبية غير التلقائية من خلال التعلم المشترك لتقدير المحاذاة والترجمة
466
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تعاني نماذج الترجمة الآلية العصبية غير التلقائية (NART) من مشكلة الوسائط المتعددة والتي تسبب عدم تناسق الترجمة مثل تكرار الرمز المميز. حاولت معظم الأساليب الأخيرة حل هذه المشكلة من خلال النمذجة الضمنية التبعيات بين المخرجات. في هذه الورقة، نقدم Alignart، الذي يرفع معلومات المحاذاة الكاملة إلى تقليل طريقة التوزيع المستهدف بشكل صريح. تقسم AlignArt مهمة ترجمة الآلة في (1) تقدير المحاذاة و (2) الترجمة مع مدخلات فك تشفير محاذاة، توجيه وحدة فك التركيز للتركيز على الترجمة المبسطة الواحدة المبسطة. لتخفيف مشكلة تقدير المحاذاة، فإننا نقترح كذلك طريقة تحلل المحاذاة الجديدة. تظهر تجاربنا أن Alignart تفوق النماذج السابقة غير التكرارية التي تركز على تخفيض طريقة صريحة على WMT14 EN↔DE و WMT16 RO → EN. علاوة على ذلك، تحقق Alignart درجات بلو مماثلة لتلك النماذج القائمة على التصنيف الزمني للدولة من الفنون على WMT14 En↔de. نلاحظ أيضا أن Alignart يعالج بشكل فعال مشكلة تكرار الرمز المميز حتى دون تقطير المعرفة على مستوى التسلسل.
Non-autoregressive neural machine translation (NART) models suffer from the multi-modality problem which causes translation inconsistency such as token repetition. Most recent approaches have attempted to solve this problem by implicitly modeling dependencies between outputs. In this paper, we introduce AligNART, which leverages full alignment information to explicitly reduce the modality of the target distribution. AligNART divides the machine translation task into (i) alignment estimation and (ii) translation with aligned decoder inputs, guiding the decoder to focus on simplified one-to-one translation. To alleviate the alignment estimation problem, we further propose a novel alignment decomposition method. Our experiments show that AligNART outperforms previous non-iterative NART models that focus on explicit modality reduction on WMT14 En↔De and WMT16 Ro→En. Furthermore, AligNART achieves BLEU scores comparable to those of the state-of-the-art connectionist temporal classification based models on WMT14 En↔De. We also observe that AligNART effectively addresses the token repetition problem even without sequence-level knowledge distillation.
References used
https://aclanthology.org/
rate research
Read More
Non-autoregressive neural machine translation, which decomposes the dependence on previous target tokens from the inputs of the decoder, has achieved impressive inference speedup but at the cost of inferior accuracy. Previous works employ iterative d
ecoding to improve the translation by applying multiple refinement iterations. However, a serious drawback is that these approaches expose the serious weakness in recognizing the erroneous translation pieces. In this paper, we propose an architecture named RewriteNAT to explicitly learn to rewrite the erroneous translation pieces. Specifically, RewriteNAT utilizes a locator module to locate the erroneous ones, which are then revised into the correct ones by a revisor module. Towards keeping the consistency of data distribution with iterative decoding, an iterative training strategy is employed to further improve the capacity of rewriting. Extensive experiments conducted on several widely-used benchmarks show that RewriteNAT can achieve better performance while significantly reducing decoding time, compared with previous iterative decoding strategies. In particular, RewriteNAT can obtain competitive results with autoregressive translation on WMT14 En-De, En-Fr and WMT16 Ro-En translation benchmarks.
Non-autoregressive Transformer is a promising text generation model. However, current non-autoregressive models still fall behind their autoregressive counterparts in translation quality. We attribute this accuracy gap to the lack of dependency model
ing among decoder inputs. In this paper, we propose CNAT, which learns implicitly categorical codes as latent variables into the non-autoregressive decoding. The interaction among these categorical codes remedies the missing dependencies and improves the model capacity. Experiment results show that our model achieves comparable or better performance in machine translation tasks than several strong baselines.
Non-Autoregressive machine Translation (NAT) models have demonstrated significant inference speedup but suffer from inferior translation accuracy. The common practice to tackle the problem is transferring the Autoregressive machine Translation (AT) k
nowledge to NAT models, e.g., with knowledge distillation. In this work, we hypothesize and empirically verify that AT and NAT encoders capture different linguistic properties of source sentences. Therefore, we propose to adopt multi-task learning to transfer the AT knowledge to NAT models through encoder sharing. Specifically, we take the AT model as an auxiliary task to enhance NAT model performance. Experimental results on WMT14 En-De and WMT16 En-Ro datasets show that the proposed Multi-Task NAT achieves significant improvements over the baseline NAT models. Furthermore, the performance on large-scale WMT19 and WMT20 En-De datasets confirm the consistency of our proposed method. In addition, experimental results demonstrate that our Multi-Task NAT is complementary to knowledge distillation, the standard knowledge transfer method for NAT.
Back-translation (BT) has become one of the de facto components in unsupervised neural machine translation (UNMT), and it explicitly makes UNMT have translation ability. However, all the pseudo bi-texts generated by BT are treated equally as clean da
ta during optimization without considering the quality diversity, leading to slow convergence and limited translation performance. To address this problem, we propose a curriculum learning method to gradually utilize pseudo bi-texts based on their quality from multiple granularities. Specifically, we first apply crosslingual word embedding to calculate the potential translation difficulty (quality) for the monolingual sentences. Then, the sentences are fed into UNMT from easy to hard batch by batch. Furthermore, considering the quality of sentences/tokens in a particular batch are also diverse, we further adopt the model itself to calculate the fine-grained quality scores, which are served as learning factors to balance the contributions of different parts when computing loss and encourage the UNMT model to focus on pseudo data with higher quality. Experimental results on WMT 14 En-Fr, WMT 14 En-De, WMT 16 En-Ro, and LDC En-Zh translation tasks demonstrate that the proposed method achieves consistent improvements with faster convergence speed.
Multilingual neural machine translation models typically handle one source language at a time. However, prior work has shown that translating from multiple source languages improves translation quality. Different from existing approaches on multi-sou
rce translation that are limited to the test scenario where parallel source sentences from multiple languages are available at inference time, we propose to improve multilingual translation in a more common scenario by exploiting synthetic source sentences from auxiliary languages. We train our model on synthetic multi-source corpora and apply random masking to enable flexible inference with single-source or bi-source inputs. Extensive experiments on Chinese/English-Japanese and a large-scale multilingual translation benchmark show that our model outperforms the multilingual baseline significantly by up to +4.0 BLEU with the largest improvements on low-resource or distant language pairs.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
